A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914169605849088 |
|---|---|
| author | Mo, Mengjingcheng Tong, Xinyang Tan, Mingpi Leng, Jiaxu Zheng, Jiankang Liu, Yiran Chen, Haosheng Gan, Ji Li, Weisheng Gao, Xinbo |
| author_facet | Mo, Mengjingcheng Tong, Xinyang Tan, Mingpi Leng, Jiaxu Zheng, Jiankang Liu, Yiran Chen, Haosheng Gan, Ji Li, Weisheng Gao, Xinbo |
| contents | While unmanned aerial vehicles (UAVs) offer wide-area, high-altitude coverage for anomaly detection, they face challenges such as dynamic viewpoints, scale variations, and complex scenes. Existing datasets and methods, mainly designed for fixed ground-level views, struggle to adapt to these conditions, leading to significant performance drops in drone-view scenarios. To bridge this gap, we introduce A2Seek (Aerial Anomaly Seek), a large-scale, reasoning-centric benchmark dataset for aerial anomaly understanding. This dataset covers various scenarios and environmental conditions, providing high-resolution real-world aerial videos with detailed annotations, including anomaly categories, frame-level timestamps, region-level bounding boxes, and natural language explanations for causal reasoning. Building on this dataset, we propose A2Seek-R1, a novel reasoning framework that generalizes R1-style strategies to aerial anomaly understanding, enabling a deeper understanding of "Where" anomalies occur and "Why" they happen in aerial frames. To this end, A2Seek-R1 first employs a graph-of-thought (GoT)-guided supervised fine-tuning approach to activate the model's latent reasoning capabilities on A2Seek. Then, we introduce Aerial Group Relative Policy Optimization (A-GRPO) to design rule-based reward functions tailored to aerial scenarios. Furthermore, we propose a novel "seeking" mechanism that simulates UAV flight behavior by directing the model's attention to informative regions. Extensive experiments demonstrate that A2Seek-R1 achieves up to a 22.04% improvement in AP for prediction accuracy and a 13.9% gain in mIoU for anomaly localization, exhibiting strong generalization across complex environments and out-of-distribution scenarios. Our dataset and code are released at https://2-mo.github.io/A2Seek/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21962 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding Mo, Mengjingcheng Tong, Xinyang Tan, Mingpi Leng, Jiaxu Zheng, Jiankang Liu, Yiran Chen, Haosheng Gan, Ji Li, Weisheng Gao, Xinbo Computer Vision and Pattern Recognition While unmanned aerial vehicles (UAVs) offer wide-area, high-altitude coverage for anomaly detection, they face challenges such as dynamic viewpoints, scale variations, and complex scenes. Existing datasets and methods, mainly designed for fixed ground-level views, struggle to adapt to these conditions, leading to significant performance drops in drone-view scenarios. To bridge this gap, we introduce A2Seek (Aerial Anomaly Seek), a large-scale, reasoning-centric benchmark dataset for aerial anomaly understanding. This dataset covers various scenarios and environmental conditions, providing high-resolution real-world aerial videos with detailed annotations, including anomaly categories, frame-level timestamps, region-level bounding boxes, and natural language explanations for causal reasoning. Building on this dataset, we propose A2Seek-R1, a novel reasoning framework that generalizes R1-style strategies to aerial anomaly understanding, enabling a deeper understanding of "Where" anomalies occur and "Why" they happen in aerial frames. To this end, A2Seek-R1 first employs a graph-of-thought (GoT)-guided supervised fine-tuning approach to activate the model's latent reasoning capabilities on A2Seek. Then, we introduce Aerial Group Relative Policy Optimization (A-GRPO) to design rule-based reward functions tailored to aerial scenarios. Furthermore, we propose a novel "seeking" mechanism that simulates UAV flight behavior by directing the model's attention to informative regions. Extensive experiments demonstrate that A2Seek-R1 achieves up to a 22.04% improvement in AP for prediction accuracy and a 13.9% gain in mIoU for anomaly localization, exhibiting strong generalization across complex environments and out-of-distribution scenarios. Our dataset and code are released at https://2-mo.github.io/A2Seek/. |
| title | A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.21962 |